Articles

ADMISSIBILITY IN THE GENERAL GROWTH CURVE MODEL WITH RESPECT TO RESTRICTED |PARAMETER SETS UNDER MATRIX LOSS FUNCTION

  • ZHANG Shang-Li ,
  • QIN Hong
Expand
  • School of Science, Beijing Jiaotong University, Beijing 100044, China

Received date: 2008-11-10

  Revised date: 2009-06-11

  Online published: 2010-01-20

Supported by

This research was partially supported by the NNSF of China (60736047, 10671080) and NCET (06-672).

Abstract

In this paper, we study the issue of admissibility in the growth curve model with respect to restricted parameter sets under matrix loss function. We obtain some necessary and sufficient conditions that the linear estimators of $KBL$ are admissible in the class of
homogeneous linear estimators and in the class of  non-homogeneous linear estimators under the growth curve model with respect to
restricted parameter sets, respectively.

Cite this article

ZHANG Shang-Li , QIN Hong . ADMISSIBILITY IN THE GENERAL GROWTH CURVE MODEL WITH RESPECT TO RESTRICTED |PARAMETER SETS UNDER MATRIX LOSS FUNCTION[J]. Acta mathematica scientia, Series B, 2010 , 30(1) : 27 -38 . DOI: 10.1016/S0252-9602(10)60019-7

References

[1]  Baksalary J K, Markiewicz A. A matrix inequality and admissibility of linear estimator with respect to the mean square error matrix criterion. Linear Algebra Appl, 1989, 112: 9--18

[2] Cohen A. All admissibility estimates of the mean vector. Ann Math Statist, 1966, 37: 458--463

[3] Deng Q R, Chen J B. Admissibility of nonhomogeneous linear estimators in linear model with respect to an incomplete ellipsoidal restriction under matrix loss function. Chinese Ann Math, 1997, 18A: 33--40

[4] GroB J, Markiewicz A. Characterizations of admissible linear estimators in the linear model. Linear Algebra Appl, 2004, 388: 239--248

[5] Hoffmann K. Admissibility of linear estimation with respect to restricted parameter sets. Math Oper Statist Ser Statist, 1977, 8: 425--438

[6] Hoffmann K. All admissible linear estimators of the regression parameter vecter in the case of an arbitrary parameter subset. J Statist Plann Inference, 1995, 48: 371--377

[7] LaMotte L R. Admissibility in linear estimation. Ann Math Statist, 1982, 10: 245--255

[8] Lee J C. Prediction and estimation of growth curves with special covariance structure. J Amer Statist Assoc, 1988, 83: 432--440

[9] Liu G, Zhang S L. Admissibility of linear estimators of the regression coefficients in the growth curve model. Acta Math  Sci, 2009, 29A: 607--612 (in Chinese)

[10] Lu C Y. Admissibility of inhomogeneous linear estimators in linear model with respect to an incomplete ellipsoidal restriction. Commun Statist Theory Methods, 1995, 24: 1737--1742

[11] Mathew T. Admissible linear estimation in singular models with respect to restricted parameter set. Commun Statist Theory and
Methods, 1985, 14: 491--498

[12] Markiewicz A. Estimation and experiments comparison with respect to the matrix risk. Linear Algebra Appl, 2002, 354: 213--222

[13] Marquardt D W. Generalized inverses, ridge regression, biased linear estimation and nonlinear estimation. Technometrics, 1970, 12: 591--612

[14] Perlman M D. Reduced mean square error estimation for several parameters. Sarkhya B, 1972:  89--92

[15] Polthoff R F, Roy S N. A generalized multivirate analysis of variance model useful especially for growth cure model. Biometrika, 1964,  51: 313--326

[16] Qin H, Wu M, Peng J H. Generalized admissibility of linear estimator in multiple linear model with restricted parameter set. Acta Math Sci, 2002, 22A: 427--432 (in Chinese)

[17] Rao C R. Estimation of parameter in a linear models. Ann Math Statist, 1976, 4: 1023--1037

[18] Rao C R. Prediction of future observation in growth curve models. Statit Sci, 1987, 214: 434--471

[19] Rosen D V. The growth curve model: a review. Comm Statist Theor Meth, 1991, 20: 2791--2822

[20]  Wong C S, Chang H. Estimation in a growth curve model with singular covariance. J Statist Plann Inference, 2001, 97: 323--342

[21]  Wong C  S, Masaro J, Deng W C. Estimating covariance in growth cueve model. Linear Algebra Appl, 1995, 214: 103--118

[22]  Wu Q G. Some results on parameter estimation in extended growth curve models. J Statist Plann Inference, 2000, 88: 285--300

[23]  Zhang B X, Zhu X H. Gauss-Markov and weighted least-squares estimation under a growth curve model. Linear Algebra Appl, 2000,  321: 387--398

[24] Zhang S L, Gui W H. Admissibility of linear estimators in a growth curve model subject to an incomplete ellipsoidal restriction. Acta Math  Sci, 2008, 28B: 194--200

[25]  Zhang S L, Qin H. Universal admissibility of linear estimators in growth curve model with respect to restricted parameter sets. Acta Math  Sci, 2008, 28A: 523--529 (in Chinese)

[26]  Zhu X H, Lu C Y. Admissibility of linear estimators in linear model. Chinese Ann Math, 1987, 8A: 220--226

 

Outlines

/